PAMI TC November 2002 Newsletter


		IEEE Computer Society Technical Committee on
		  Pattern Analysis and Machine Intelligence
				Newsletter

			     November 4, 2002


TABLE OF CONTENTS

PAMI Technical Committee (PAMI-TC) Information
	Web site
	Chair
	How to Join the PAMI-TC

Call for Proposals
	United States' National Science Foundation ITR Program

Call for Papers at Upcoming PAMI-TC-sponsored Conferences and Workshops
	4th International  Conference on Audio and Video Based
	   Biometric Person Authentication, 9-11 June 2003

********************************************************************************

PAMI-TC INFORMATION

The web page for the PAMI-TC is now located at

	http://tab.computer.org/pamitc/

Questions, comments, and suggestions for the PAMI-TC should be sent to the
current TC chair:

	Charles R. Dyer

	Department of Computer Sciences   Office  6379 Comp Sci & Stat Bldg
	University of Wisconsin-Madison   Tel     +1 608-262-1965
	1210 West Dayton Street           Fax     +1 608-262-9777
	Madison, WI  53706-1685           Dept    +1 608-262-1204
	USA                               E-mail  dyer@cs.wisc.edu
       		                          Web     http://www.cs.wisc.edu/~dyer/


The recipient list of this PAMI-TC electronic newsletter and other publications,
e.g., the IAPR Newsletter, is determined by the IEEE Computer Society's list.
To join this technical committee, or to update your information, especially
your email address, visit the following web site and fill in the online form.

	http://www.computer.org/TCsignup/


****************************************************************************

CALL FOR PROPOSALS

The area of pattern discovery has become critical both because of
the  scientific  challenges  involved  in  dealing  with  massive
amounts of data and because of its relevance to national security
needs.  While  steady  incremental  progress  based  on classical
paradigms  have  made  solutions  to  a  few  specific   problems
technologically feasible, for more complex tasks there is a clear
need and scope for  fundamental  research  to  exploit  available
computational  resources  and  more  advanced analytics together.
Recent progress has  been  based  on  ideas  drawn  from  several
disciplines  e.g.,  computer  science,  engineering, mathematics,
statistics, biology, medicine etc.

The  United  States'  National  Science  Foundation   Information
Technology  Research (ITR) program, which stresses innovative and
multidisciplinary approaches for significant problems, would be a
good vehicle for funding basic research in pattern discovery.

Some technical issues are: High dimensional data modeling,  novel
clustering  techniques,  combination  of ensemble of classifiers,
methods for scaling up supervised learning algorithms. Active and
reinforced  learning,  learning  and  inference  associated  with
graphical models including factor graphs, MRFs.  Kernel machines,
transductive  inference  techniques. Deformable templates; (time)
sequential  and  3D  pattern  recognition.  Use  of  (stochastic)
grammars.  Fusion  of multi-modal data from heterogeneous sensors
in complex pattern recognition tasks; novel fusion paradigms.

Current   applications  may  include:  Biometrics  e.g.,    face,
fingerprint,   voice,   iris,   gait  recognition.  Tracking  and
surveillance including  bio-surveillance  possibly  arising  from
epidemiological   considerations   e.g.,   spatio-temporal  event
detection.  Recognition and discovery of information arising from
fusion  of  data  obtained  via  e.g.,  global  sensing  systems,
biological,  infrared  and  other  detectors.    Biomedical   and
financial forecasting applications may also be considered.

In order to facilitate review and proper tracking  of  proposals,
submission  should be accompanied by the following designation of
NSF program unit:

Large ITR projects:	CISE directorate.
Medium ITR projects:	CISE directorate, CCR division
Small ITR projects:	CISE directorate, CCR division, "Special Project"
				as a program unit.

After submitting a proposal via FastLane, please let us know the proposal
number by sending an email to:

Sankar Basu
Program Director, CISE/CCR Division
National Science Foundation
4201 Wilson Blvd., Room 1145
Arlington, VA 22230
Phone: 703-292-8910
Email: sabasu@nsf.gov

ITR DEADLINES:
Large projects:  Mandatory pre-proposals November 18, 2002.
Medium projects: February 12, 2003
Small projects:  December 12, 2002.

ITR 2003 Website:
http://nsf.gov/pubs/2002/nsf02168/nsf02168.htm


****************************************************************************

CALL FOR PAPERS

   4th International  Conference on Audio and Video Based
              Biometric Person Authentication
          Guildford, United Kingdom, 9-11 June 2003

http://avbpa2003.ee.surrey.ac.uk
avbpa@eim.surrey.ac.uk

The interest in security   and  in  using  multi-modal  biometric
signal  processing  for security applications has been increasing
over the last decade. The growth of Internet and mobile telephony
has  been  an  important  factor  in  this  respect. An important
element of security  is   automatic  authentication  of  persons.
AVBPA   will bring together the leading biometric signal analysis
researchers and practioneres,  concerned  with  image  and  voice
modalities,  to  promote  the development of  robust solutions to
efficient  and  secure  communication.   The  conference   is  an
official  event  of  the  International  Association  for Pattern
Recognition (IAPR-TC14).


SCIENTIFIC PROGRAM

Thecientific program will  include    contributed  and  invited
presentations dealing with all aspects of multi-modal biometrics.
Contributions covering the topics below are  solicited.  However,
all  submissions  addressing  issues  related to biometric signal
analysis using  audio and/or   image  processing  techniques  are
strongly encouraged. Main technical areas are:

Features and Measurements
   Biometrics of face and voice
   Biometrics of finger prints
   Gait and other visual biometrics
   Still image based features
   Motion/depth based features
   Audio and lip-movements
   Multi-modal features
Biometrics and Communication
   Psychophysics of face, speech, and gesture
   Audio-visual speech recognition
   Categorization, e.g. age and gender
   Gesture interpretation
   Audio-visual tracking
   Source coding and compression
Decision Strategies
   Sensor fusion
   Decision fusion
   Protocols and benchmarking
   Databases and standardization
Architecture and Hardware
   Resolution and color in recognition
   Special sensors
   Compact embedded systems
Centralized or distributed systems

INVITED SPEAKERS

      Takeo Kanade (USA)
      Jerry Friedman (USA)
      Frederic Bimbot (USA)


CONTACT INFO AND PAPER SUBMISSION
The  web   and  e-mail addresses of AVBPA are:
 http://avbpa2003.ee.surrey.ac.uk
 avbpa@eim.surrey.ac.uk}

Paper Submission and Important Dates:

Accepted papers will be published in proceedings by Springer Verlag (LNCS).
The submitted papers should not
 exceed  8 pages and have  abstracts with approximately 200 words. Word processing templates are available www.springer.de/comp/lncs/authors.html (under Section ``Proceedings...''). The important dates are:


       Paper submission deadline:    January 10, 2003
       Acceptance notification:      February 20, 2003
       Camera ready papers:          April 1,   2003
       The conference:               June 9-11, 2003


GENERAL CO-CHAIRMEN

Josef Kittler, University of Surrey, UK
Mark Nixon, University of Southampton, UK

PROGRAM COMMITTEE

Samy Bengio (Switzerland)
Josef   Bigun   (Sweden)
Horst   Bunke   (Switzerland)
Rama Chellapa (USA)
Gerard  Chollet (France)
Farzin Deravi (United Kingdom)
Sadaoki Furui   (Japan)
Dolores Garcia-Plaza Cuellar (Spain)
Dominique Genoud  (USA)
Bernd Heisele (USA)
Anil Jain (USA)
Kenneth Jonsson  (Sweden)
Seong-Whan Lee (Korea)
Jurgen Luettin  (Switzerland)
John    Mason   (UK)
Jiri  Matas   (Czech Republic)
Bruce   Millar  (Australia)
Jonathon Phillips (USA)
Salil Prabhakar (USA)
Marek Rejman-Greene (UK)
Nalini  Ratha   (USA)
Gael    Richard (France)
Massimo Tistarelli      (Italy)
Juanjo Villanueva (Spain)
Harry   Wechsler        (USA)

***************************************************************************